We present the system submission from the FASTPARSE team for the EUD Shared
Task at IWPT 2020. We engaged with the task by focusing on efficiency. For this
we considered training costs and inference efficiency. Our models are a
combination of distilled neural dependency parsers and a rule-based system that
projects UD trees into EUD graphs. We obtained an average ELAS of 74.04 for our
official submission, ranking 4th overall.

FASTPARSE 团队针对 IWPT2020 的 EUD Shared Task 提出一种训练和推理效率结合的模型，结合神经依存解析和基于规则的系统，将 UD 树映射为 EUD 图，在官方提交中获得 74.04 的平均 ELAS，排名第 4。

高效 EUD 解析

Efficient EUD Parsing

Obtaining highly accurate depth from stereo images in real time has many
applications across computer vision and robotics, but in some contexts, upper
bounds on power consumption constrain the feasible hardware to embedded
platforms such as FPGAs. Whilst various stereo algorithms have been deployed on
these platforms, usually cut down to better match the embedded architecture,
certain key parts of the more advanced algorithms, e.g. those that rely on
unpredictable access to memory or are highly iterative in nature, are difficult
to deploy efficiently on FPGAs, and thus the depth quality that can be achieved
is limited. In this paper, we leverage a FPGA-CPU chip to propose a novel,
sophisticated, stereo approach that combines the best features of SGM and
ELAS-based methods to compute highly accurate dense depth in real time. Our
approach achieves an 8.7% error rate on the challenging KITTI 2015 dataset at
over 50 FPS, with a power consumption of only 5W.

本文提出一种结合 SGM 和 ELAS 方法的 FPGA-CPU 芯片的立体图像算法，实现了高效和高精度的深度数据点云的计算，并在 KITTI 2015 数据集上以 50FPS 的速度和 5W 的功率消耗下，达到了仅 8.7％的误差率。